© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 40182
    Prev
    Next
    INDEX
    Explanations

    financial and accounting-related terms and concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    otten
    -0.08
    .opend
    -0.07
    mini
    -0.06
    ISTA
    -0.06
    irut
    -0.06
    ANCH
    -0.06
    anc
    -0.06
    ista
    -0.06
    æĿŁ
    -0.06
    ADER
    -0.06
    POSITIVE LOGITS
     Net
    0.08
     net
    0.07
    _contrib
    0.07
     Fund
    0.07
    iban
    0.06
    itzer
    0.06
    _net
    0.06
     reluct
    0.06
     Contrib
    0.06
     contributions
    0.06
    Activations Density 0.004%

    No Known Activations